AlloSpatial：面向基础模型空间推理的智能体调控框架

摘要

多模态基础模型（MFMs）已取得显著进展，但在物理世界的空间推理方面仍然脆弱。关键瓶颈在于它们无法将局部自我中心观测转化为全局异我中心空间表征。为解决这一问题，我们提出AlloSpatial——一种面向基础模型的异我中心空间认知智能体框架。AlloSpatial引入了World2Mind，一个即插即用的认知映射沙盒，可将自我中心观测转化为结构化异我中心先验，包括支持对象拓扑、几何关系、可通过性及轨迹查询的异我中心空间树与路线图。为了在噪声重构和模糊视觉证据下可靠利用这些先验，AlloSpatial提出了一种空间推理约束机制，用于工具使用判断、模态解耦线索收集以及几何-语义仲裁。我们进一步通过冷启动强化学习，结合约束门控轨迹级奖励，在Qwen3-VL中内化这一过程。在VSI-Bench和MindCube上的实验表明，AlloSpatial在免训练设置下将专有模型的性能提升了5%-18%；即便移除视觉输入，仅使用异我中心空间树也能支持强大的空间推理。训练后的AlloSpatial智能体进一步超越了更大的通用模型及具有竞争力的空间基线，这表明结构化的异我中心表征、主动工具使用以及可验证的推理为构建具备空间能力的基础模型提供了一条有前景的路径。

English

Multimodal Foundation Models (MFMs) have made substantial progress, yet remain fragile in spatial reasoning over the physical world. A key bottleneck lies in their inability to transform local egocentric observations into a global allocentric spatial representation. To address this, we propose AlloSpatial, an agentic framework for allocentric spatial cognition in foundation models. AlloSpatial introduces World2Mind, a plug-and-play cognitive mapping sandbox that converts egocentric observations into structured allocentric priors, including Allocentric-Spatial Trees and route maps that support querying object topology, geometric relations, passability, and trajectories. To utilize these priors reliably under noisy reconstruction and ambiguous visual evidence, AlloSpatial introduces a Spatial Reasoning Harness for tool-use judgment, modality-decoupled cue collection, and geometry-semantic arbitration. We further internalize this process in Qwen3-VL through cold-start reinforcement learning with a harness-gated trajectory-level reward. Experiments on VSI-Bench and MindCube show that AlloSpatial improves proprietary models by 5%-18% in a training-free setting, while ASTs alone support strong spatial reasoning even when visual inputs are removed. The trained AlloSpatial agents further outperform larger general-purpose models and competitive spatial baselines, suggesting that structured allocentric representations, active tool use, and verifiable reasoning offer a promising route toward spatially capable foundation models.